LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Magnum V2 123B by anthracite-org

 »  All LLMs  »  anthracite-org  »  Magnum V2 123B   URL Share it on

  49   

Magnum V2 123B is an open-source language model by anthracite-org. Features: 123b LLM, VRAM: 207.6GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.16.

Base model:finetune:mistralai/... Base model:mistralai/mistral-l...   Chat   Conversational Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/nopm cl... Dataset:doctor-shotgun/c2-sthe...   De   En   Endpoints compatible   Es   Fr   Instruct   It   Ja   Mistral   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/anthracite-org/magnum-v2-123b 

Magnum V2 123B Benchmarks

LLME Score: 0.15787
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magnum V2 123B (anthracite-org/magnum-v2-123b)
🌟 Advertise your project 🚀

Magnum V2 123B Parameters and Internals

Model Type 
text generation
Additional Notes 
This is the sixth model in a series to replicate the prose quality of Claude 3 models, specifically Sonnet and Opus.
Supported Languages 
en (supported), fr (supported), de (supported), es (supported), it (supported), pt (supported), ru (supported), zh (supported), ja (supported)
Training Details 
Data Sources:
anthracite-org/Stheno-Data-Filtered, anthracite-org/kalo-opus-instruct-22k-no-refusal, anthracite-org/nopm_claude_writing_fixed
Methodology:
Instruct tuning with Mistral formatting
Training Time:
1.5 epochs
Hardware Used:
8x AMD Instinct™ MI300X Accelerators
Input Output 
Input Format:
Mistral formatting: [INST] USER MESSAGE[/INST]
Accepted Modalities:
text
Performance Tips:
Recommend replacing misconfigured SillyTavern presets with Context and Instruct presets.
LLM NameMagnum V2 123B
Repository 🤗https://huggingface.co/anthracite-org/magnum-v2-123b 
Base Model(s)  Mistral Large Instruct 2407   mistralai/Mistral-Large-Instruct-2407
Model Size123b
Required VRAM207.6 GB
Updated2026-04-08
Maintaineranthracite-org
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-51   4.8 GB: 2-of-51   4.9 GB: 3-of-51   4.8 GB: 4-of-51   4.8 GB: 5-of-51   4.8 GB: 6-of-51   4.9 GB: 7-of-51   4.8 GB: 8-of-51   4.8 GB: 9-of-51   4.8 GB: 10-of-51   4.9 GB: 11-of-51   4.8 GB: 12-of-51   4.8 GB: 13-of-51   4.8 GB: 14-of-51   4.9 GB: 15-of-51   4.8 GB: 16-of-51   4.8 GB: 17-of-51   4.8 GB: 18-of-51   4.9 GB: 19-of-51   4.8 GB: 20-of-51   4.8 GB: 21-of-51   4.8 GB: 22-of-51   4.9 GB: 23-of-51   4.8 GB: 24-of-51   4.8 GB: 25-of-51   4.8 GB: 26-of-51   4.9 GB: 27-of-51   4.8 GB: 28-of-51   4.8 GB: 29-of-51   4.8 GB: 30-of-51   4.9 GB: 31-of-51   4.8 GB: 32-of-51   4.8 GB: 33-of-51   4.8 GB: 34-of-51   4.9 GB: 35-of-51   4.8 GB: 36-of-51   4.8 GB: 37-of-51   4.8 GB: 38-of-51   4.9 GB: 39-of-51   4.8 GB: 40-of-51   4.8 GB: 41-of-51   4.8 GB: 42-of-51   4.9 GB: 43-of-51
Supported Languagesen fr de es it pt ru zh ja
Model ArchitectureMistralForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.43.4
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Magnum V2 123B

Best Alternatives
Context / RAM
Downloads
Likes
Behemoth R1 123B V2128K / 226.4 GB115920
Behemoth X 123B V2128K / 217.2 GB76316
Behemoth ReduX 123B V1128K / 217.2 GB3468
ML2 123B Magnum Diamond128K / 212.4 GB1111
Gigaberg Mistral Large 123B128K / 222 GB62
Behemoth 123B V2128K / 221.6 GB5210
Cakrawala 123B128K / 222 GB84
Behemoth 123B V1128K / 221.6 GB4644
Magnum V4 123B128K / 222 GB1731
Lumikabra 123B V0.4128K / 216.7 GB8012
Note: green Score (e.g. "73.2") means that the model is better than anthracite-org/magnum-v2-123b.

Rank the Magnum V2 123B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer